AI Engineer – Full Stack GenAI

Umanist Staffing LLC; Pune District; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Umanist Staffing LLC is seeking an AI Engineer with strong Full-Stack GenAI capabilities to build, deploy, and scale production-grade Generative AI applications in Pune (Viman Nagar).

You will work in a hybrid mode, collaborate across AI and engineering teams, and contribute to RAG pipelines, LLM integrations, and cloud deployments using Azure OpenAI or AWS Bedrock.

The role requires 4+ years of experience with Next.js, TypeScript, Python, and hands-on GenAI/LLM productionization.

Qualifications

• 4+ years of software/AI engineering experience.
• Hands-on Full-Stack development with Next.js, TypeScript, and Python.
• Proven experience building and productionizing GenAI/LLM applications.

Responsibilities

• Build and optimize GenAI applications with Next.js, TypeScript, and Python.
• Design, develop, and deploy production-grade AI systems with RAG.
• Develop LLM-powered content generation, summarization, and metadata enrichment.
• Work with LangChain, LlamaIndex, DSPy, and transformers.
• Implement LLM pipelines with prompts, embeddings, and vector storage.
• Deploy and manage LLM apps on Azure OpenAI or AWS Bedrock.
• Implement LLMOps and observability for latency, cost, accuracy, data drift.
• Collaborate across AI and engineering teams to deliver scalable solutions.

Skills

Next.js

TypeScript

Python

LLM apps

RAG

LangChain

LlamaIndex

DSPy

Hugging Face Transformers

Azure OpenAI

AWS Bedrock

Azure

Cloud services

Docker

CI/CD pipelines

GitHub Actions

Argo

Tools

Docker

GitHub Actions

Argo

Job description

Only immediate joiner to 30days of notice will be considered Not more than that.

AI Engineer -- Full Stack GenAI

Location: Viman Nagar, Pune

Experience: 4+ Years

Work Mode: Hybrid

Working Hours: 11:00 AM -- 8:00 PM

About the Role

We are looking for an AI Engineer with strong Full-Stack development experience to build, deploy, and scale production-grade Generative AI applications. The ideal candidate should be hands-on with Next.js, TypeScript, Python, LLM applications, RAG, cloud platforms, and LLMOps.

Key Responsibilities

• Build and optimize full-stack GenAI applications using Next.js, TypeScript, and Python.
• Design, develop, and deploy production-grade AI systems, including Retrieval-Augmented Generation (RAG) solutions for search and discovery.
• Develop and integrate LLM-powered applications for content generation, summarization, metadata enrichment, and other AI use cases.
• Work with modern GenAI frameworks such as LangChain, LlamaIndex, DSPy, and Hugging Face Transformers.
• Implement advanced RAG pipelines, including prompt engineering, chunking strategies, embeddings, and vector database integration.
• Deploy and manage LLM applications using cloud-based services such as Azure OpenAI or AWS Bedrock.
• Implement LLMOps and observability to monitor latency, cost, accuracy, hallucination, toxicity, and data drift.
• Collaborate across the AI and engineering stack to build scalable, reliable, and production-ready solutions.

Mandatory Requirements

• 4+ years of relevant professional experience in software, AI engineering.
• Strong Full-Stack development experience with hands-on expertise in:
  • Next.js
  • TypeScript
  • Python
• Demonstrable experience building and productionizing LLM/GenAI applications.
• Strong practical knowledge of RAG architecture, including:
  • Prompt engineering
  • Chunking strategies
  • Embeddings
  • Vector databases such as Pinecone, Weaviate, or Milvus
• Hands-on experience with at least one modern GenAI/LLM framework such as LangChain, LlamaIndex, DSPy, or Hugging Face Transformers.
• Experience with managed LLM services such as Azure OpenAI Service or AWS Bedrock.
• Strong foundational knowledge of Azure or AWS cloud services.
• Experience with containerization and deployment tools such as Docker and CI/CD pipelines (GitHub Actions, Argo, or similar).
• Experience deploying and managing production-grade AI/LLM solutions.
• Understanding of LLMOps, observability, and monitoring for AI applications.

Nice-to-Have Skills

• Experience with agentic AI workflows using tools such as AutoGen or CrewAI.
• Exposure to multimodal AI models involving text, images, or other data types.
• Knowledge of advanced LLM fine-tuning techniques such as LoRA or QLoRA.
• Experience with AKS/EKS, serverless functions, and cloud storage.
• Strong SQL skills, particularly ClickHouse.
• Experience with inference cost optimization and AI application performance tuning.
• Experience with monitoring tools such as OpenTelemetry and Prometheus.
• Knowledge of model registries and MLOps best practices.